Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pton
    -0.06
    нув
    -0.06
     postings
    -0.06
    ardım
    -0.06
    SR
    -0.06
    _tag
    -0.06
    UnitOfWork
    -0.06
     prosecutors
    -0.06
    .BadRequest
    -0.06
     зад
    -0.06
    POSITIVE LOGITS
    	arr
    0.07
    /St
    0.07
     manipulating
    0.07
    	Y
    0.07
    �
    0.06
     $.
    0.06
     předpis
    0.06
     TEMPLATE
    0.06
     deque
    0.06
    .enemy
    0.06
    Act Density 0.000%

    No Known Activations